{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AK2GEZCYSXEBV7BYGKG5LBHOKV","short_pith_number":"pith:AK2GEZCY","schema_version":"1.0","canonical_sha256":"02b462645895c81afc38328dd584ee5540eeaaacb959fca7818f341334640050","source":{"kind":"arxiv","id":"2412.06781","version":1},"attestation_state":"computed","paper":{"title":"Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David Picard, Loic Landrieu, Nicolas Dufour, Vicky Kalogeiton","submitted_at":"2024-12-09T18:59:04Z","abstract_excerpt":"Global visual geolocation predicts where an image was captured on Earth. Since images vary in how precisely they can be localized, this task inherently involves a significant degree of ambiguity. However, existing approaches are deterministic and overlook this aspect. In this paper, we aim to close the gap between traditional geolocalization and modern generative methods. We propose the first generative geolocation approach based on diffusion and Riemannian flow matching, where the denoising process operates directly on the Earth's surface. Our model achieves state-of-the-art performance on th"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.06781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T18:59:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c357a91e4c4c733d1666cceb582d971486da480ec01a9cdc5837e140c193b6a9","abstract_canon_sha256":"58f538175ed21baa6874b6c3d7da1bd5420b1c959b3e4bd523b6493f39184439"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:37.793547Z","signature_b64":"9MDdx9QHpwvhdm+iWzaUDonMMX7uiAjNqZEaInWxAEShJ9umr/jBVcZeuAdKNu5YcqZfBhjutiYm7Hb6rBepCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02b462645895c81afc38328dd584ee5540eeaaacb959fca7818f341334640050","last_reissued_at":"2026-07-05T09:46:37.793009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:37.793009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David Picard, Loic Landrieu, Nicolas Dufour, Vicky Kalogeiton","submitted_at":"2024-12-09T18:59:04Z","abstract_excerpt":"Global visual geolocation predicts where an image was captured on Earth. Since images vary in how precisely they can be localized, this task inherently involves a significant degree of ambiguity. However, existing approaches are deterministic and overlook this aspect. In this paper, we aim to close the gap between traditional geolocalization and modern generative methods. We propose the first generative geolocation approach based on diffusion and Riemannian flow matching, where the denoising process operates directly on the Earth's surface. Our model achieves state-of-the-art performance on th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06781","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.06781/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.06781","created_at":"2026-07-05T09:46:37.793071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06781v1","created_at":"2026-07-05T09:46:37.793071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06781","created_at":"2026-07-05T09:46:37.793071+00:00"},{"alias_kind":"pith_short_12","alias_value":"AK2GEZCYSXEB","created_at":"2026-07-05T09:46:37.793071+00:00"},{"alias_kind":"pith_short_16","alias_value":"AK2GEZCYSXEBV7BY","created_at":"2026-07-05T09:46:37.793071+00:00"},{"alias_kind":"pith_short_8","alias_value":"AK2GEZCY","created_at":"2026-07-05T09:46:37.793071+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01277","citing_title":"GeoLocSFT: Efficient Visual Geolocation via Supervised Fine-Tuning of Multimodal Foundation Models","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AK2GEZCYSXEBV7BYGKG5LBHOKV","json":"https://pith.science/pith/AK2GEZCYSXEBV7BYGKG5LBHOKV.json","graph_json":"https://pith.science/api/pith-number/AK2GEZCYSXEBV7BYGKG5LBHOKV/graph.json","events_json":"https://pith.science/api/pith-number/AK2GEZCYSXEBV7BYGKG5LBHOKV/events.json","paper":"https://pith.science/paper/AK2GEZCY"},"agent_actions":{"view_html":"https://pith.science/pith/AK2GEZCYSXEBV7BYGKG5LBHOKV","download_json":"https://pith.science/pith/AK2GEZCYSXEBV7BYGKG5LBHOKV.json","view_paper":"https://pith.science/paper/AK2GEZCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06781&json=true","fetch_graph":"https://pith.science/api/pith-number/AK2GEZCYSXEBV7BYGKG5LBHOKV/graph.json","fetch_events":"https://pith.science/api/pith-number/AK2GEZCYSXEBV7BYGKG5LBHOKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AK2GEZCYSXEBV7BYGKG5LBHOKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AK2GEZCYSXEBV7BYGKG5LBHOKV/action/storage_attestation","attest_author":"https://pith.science/pith/AK2GEZCYSXEBV7BYGKG5LBHOKV/action/author_attestation","sign_citation":"https://pith.science/pith/AK2GEZCYSXEBV7BYGKG5LBHOKV/action/citation_signature","submit_replication":"https://pith.science/pith/AK2GEZCYSXEBV7BYGKG5LBHOKV/action/replication_record"}},"created_at":"2026-07-05T09:46:37.793071+00:00","updated_at":"2026-07-05T09:46:37.793071+00:00"}